AI-QCT plaque measurements associate with cardiovascular events in CONSERVE
Source check: Source checked. Not independent scientific confirmation.
Finding: A post hoc analysis applied Cleerly AI-QCT to coronary CT images from 747 participants in the selective-referral arm of CONSERVE. Quantified plaque burden was associated with one-year major cardiovascular events; event rates increased across plaque-volume categories. Estimated reductions in invasive angiography and costs were hypothetical decision-model outputs, not observed effects of randomized AI-guided care. Stenosis-based event discrimination was similar to clinical readers, and no blinded quantitative angiography comparison was available.
Technology: Cleerly AI-QCT; convolutional neural networks
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Validated CNNs perform image quality assessment, coronary segmentation, vascular measurement and plaque characterization. Post hoc analysis with hypothetical referral thresholds; randomized original cohort does not establish randomized AI benefit.
- Test and result
- Retrospective 747-patient plaque/event association and comparison with site CT interpretation.
- Limitation / still unknown
- AI-guided safety, realized catheterization reductions and cost savings were not tested prospectively.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC10189079/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 21 Nov 2026. Review scope: Primary full article Methods, Results and limitations plus Europe PMC bibliographic metadata; PMC full article..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.